摘要
提出了一种基于卡尔曼滤波的运动目标快速跟踪算法。针对复杂背景下彩色运动目标跟踪问题,采用基于颜色特征和形状特征相结合的方法进行目标识别。利用卡尔曼滤波器的预测功能,预测运动目标在下一帧中的位置,将图像全局搜索问题转换为局部搜索,提高了系统的实时性。实验结果表明:该算法满足移动机器人运动控制的实时性要求,实现了对运动目标的快速跟踪。
A real-time moving object tracking algorithm based on Kalman filter is proposed. The color and shape features are used together for the recognition of the moving color object in complex environment. The possible position of the moving object in the next frame is predicted by Kalman filter＇s predictive function,and the global searching scope of an image is converted to local scope, thus the system efficiency is improved. The experimental results show that the algorithm is effective in mobile robot＇ s moving control, and the speedy tracking of moving object is realized.
出处
《传感器与微系统》
CSCD
北大核心
2008年第11期66-68,71,共4页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(50775017)
国家"973"计划资助项目(2006CB300407)
